Anjie Peng
YOU?
Author Swipe
View article: Polygenic risk score and cluster-based analysis suggests links between type 2 diabetes and vascular dementia in the KARE study
Polygenic risk score and cluster-based analysis suggests links between type 2 diabetes and vascular dementia in the KARE study Open
Type 2 diabetes is an established risk factor for dementia. However, how its genetic heterogeneity affects different dementia subtypes remains unclear. In this study, we investigate the associations between genetic risk of type 2 diabetes …
View article: Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL Open
Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn, Dist…
View article: Approximating High-Order Adversarial Attacks Using Runge-Kutta Methods
Approximating High-Order Adversarial Attacks Using Runge-Kutta Methods Open
View article: Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability
Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability Open
Adversarial examples’ (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in untargeted transferability, its targeted counterpart remains c…
View article: Robust Adversarial Example Detection Algorithm Based on High-Level Feature Differences
Robust Adversarial Example Detection Algorithm Based on High-Level Feature Differences Open
The threat posed by adversarial examples (AEs) to deep learning applications has garnered significant attention from the academic community. In response, various defense strategies have been proposed, including adversarial example detectio…
View article: DSCT: a novel deep-learning framework for rapid and accurate spatial transcriptomic cell typing
DSCT: a novel deep-learning framework for rapid and accurate spatial transcriptomic cell typing Open
Unraveling complex cell-type-composition and gene-expression patterns at the cellular spatial resolution is crucial for understanding intricate cell functions in the brain. In this study, we developed Deep Neural Network-based Spatial Cell…
View article: Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability
Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability Open
Adversarial examples' (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in untargeted transferability, its targeted counterpart remains c…
View article: Mwc-Net: Multiscale Wavelet-Based Spatial-Spectral Compression Network for Hyperspectral Image
Mwc-Net: Multiscale Wavelet-Based Spatial-Spectral Compression Network for Hyperspectral Image Open
View article: Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability Open
With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in feat…
View article: Mixture of neural fields for heterogeneous reconstruction in cryo-EM
Mixture of neural fields for heterogeneous reconstruction in cryo-EM Open
Cryo-electron microscopy (cryo-EM) is an experimental technique for protein structure determination that images an ensemble of macromolecules in near-physiological contexts. While recent advances enable the reconstruction of dynamic confor…
View article: Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data Open
The modern paradigm in machine learning involves pre-training on diverse data, followed by task-specific fine-tuning. In reinforcement learning (RL), this translates to learning via offline RL on a diverse historical dataset, followed by r…
View article: ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction
ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction Open
Diffusion bridges (DB) have emerged as a promising alternative to diffusion models for imaging inverse problems, achieving faster sampling by directly bridging low- and high-quality image distributions. While incorporating measurement cons…
View article: Stochastic Deep Restoration Priors for Imaging Inverse Problems
Stochastic Deep Restoration Priors for Imaging Inverse Problems Open
Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as m…
View article: Enhancing targeted transferability via feature space fine-tuning
Enhancing targeted transferability via feature space fine-tuning Open
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. Yet, making a targeted AE transferable across unknown models remains challenging. In this paper, t…
View article: Targeted Attentional Adversarial Attack
Targeted Attentional Adversarial Attack Open
View article: A comparison study of CNN denoisers on PRNU extraction
A comparison study of CNN denoisers on PRNU extraction Open
Performance of the sensor-based camera identification (SCI) method heavily relies on the denoising filter in estimating Photo-Response Non-Uniformity (PRNU). Given various attempts on enhancing the quality of the extracted PRNU, it still s…
View article: Multi-Purpose Forensics of Image Manipulations Using Residual-Based Feature
Multi-Purpose Forensics of Image Manipulations Using Residual-Based Feature Open
The multi-purpose forensics is an important tool for forge image detection. In this paper, we propose a universal feature set for the multi-purpose forensics which is capable of simultaneously identifying several typical image manipulation…
View article: Source Camera Identification With Dual-Tree Complex Wavelet Transform
Source Camera Identification With Dual-Tree Complex Wavelet Transform Open
Sensor pattern noise (SPN) extraction is a critical stage of the sensor based source camera identification (SCI). However, the quality of the extracted SPN with the traditional discrete wavelet transform (DWT) based method is poor around s…
View article: Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot
Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot Open
Deep learning models often have complicated structures with low computational speed and the requirement of a large amount of storage space, which limits their own practical application on some devices with insufficient computing power. Thi…
View article: Median Filtering Forensics Using Multiple Models in Residual Domain
Median Filtering Forensics Using Multiple Models in Residual Domain Open
Median filtering, due to highly non-linear and content-preserving, has widely used in the multimedia security fields, such as anti-forensics, steganography, and steganalysis. In the past decade, many excellent algorithms have been proposed…
View article: Deep Residual Learning Using Data Augmentation for Median Filtering Forensics of Digital Images
Deep Residual Learning Using Data Augmentation for Median Filtering Forensics of Digital Images Open
This paper addresses the median filtering forensics for a lossy compressed image with low resolution, which is essential for the identification of fake images and fake videos. A deep residual model with training data augmentation is employ…
View article: Blind Median Filtering Detection Using Auto-Regressive Model and Markov Chain
Blind Median Filtering Detection Using Auto-Regressive Model and Markov Chain Open
Establishing the processing history of an image is important for robot vision. In this paper, an improved method for median filtering detection is proposed. That is, detect whether an image has been processed by median filtering. First, we…
View article: Revealing Traces of Image Resampling and Resampling Antiforensics
Revealing Traces of Image Resampling and Resampling Antiforensics Open
Image resampling is a common manipulation in image processing. The forensics of resampling plays an important role in image tampering detection, steganography, and steganalysis. In this paper, we proposed an effective and secure detector, …
View article: Resampling forensics based on multi-directional difference
Resampling forensics based on multi-directional difference Open
资助摘要 重采样操作常用于数字图像篡改, 重采样的盲取证受到了研究者的关注.已有的重采样取证 算法主要关注取证检测器的有效性